Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2053 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7940. Min Range: -6.7940
Max Act: 6.7628. Min Act: -0.1700
Data Index: 850307 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7940. Min Range: -6.7940
Max Act: 6.7940. Min Act: -0.1700
Data Index: 1653991 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7940. Min Range: -6.7940
Max Act: 6.6378. Min Act: -0.1700
Data Index: 4286937 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7940. Min Range: -6.7940
Max Act: 6.6065. Min Act: -0.1700
Data Index: 1653996 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7940. Min Range: -6.7940
Max Act: 6.6065. Min Act: -0.1700
Data Index: 7302407 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7940. Min Range: -6.7940
Max Act: 6.5753. Min Act: -0.1700
Data Index: 2239373 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7940. Min Range: -6.7940
Max Act: 6.5753. Min Act: -0.1700
Data Index: 7447501 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7940. Min Range: -6.7940
Max Act: 6.5440. Min Act: -0.1700
Data Index: 1653998 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7940. Min Range: -6.7940
Max Act: 6.5753. Min Act: -0.1700
Data Index: 6319208 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7940. Min Range: -6.7940
Max Act: 6.5128. Min Act: -0.1700
Data Index: 3096084 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7940. Min Range: -6.7940
Max Act: 6.5440. Min Act: -0.1700
Data Index: 1978653 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7940. Min Range: -6.7940
Max Act: 6.5128. Min Act: -0.1700
Data Index: 8618682 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7940. Min Range: -6.7940
Max Act: 6.4503. Min Act: -0.1700
Data Index: 8680917 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7940. Min Range: -6.7940
Max Act: 6.4503. Min Act: -0.1700
Data Index: 2855662 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7940. Min Range: -6.7940
Max Act: 6.4503. Min Act: -0.1700
Data Index: 4328425 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7940. Min Range: -6.7940
Max Act: 6.4190. Min Act: -0.1700
Data Index: 7708344 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7940. Min Range: -6.7940
Max Act: 6.4503. Min Act: -0.1700
Data Index: 5960395 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7940. Min Range: -6.7940
Max Act: 6.3878. Min Act: -0.1700
Data Index: 2416515 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7940. Min Range: -6.7940
Max Act: 6.3878. Min Act: -0.1700
Data Index: 4178092 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7940. Min Range: -6.7940
Max Act: 6.3878. Min Act: -0.1700
Data Index: 7137683 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19